© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3299
    Prev
    Next
    INDEX
    Explanations

    the verb "come" and the preposition "to"

    oai_token-act-pair · gemini-2.0-flash

    comes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.61
     &___
    -0.61
    droje
    -0.60
    ))->
    -0.60
     enfans
    -0.59
     milliers
    -0.58
     jspb
    -0.58
    %
    -0.57
    ))).
    -0.57
    _));
    -0.57
    POSITIVE LOGITS
    AddHtmlAttribute
    0.58
    MLLoader
    0.48
    StructEnd
    0.44
    脚注の使い方
    0.42
     Dick
    0.42
     Centi
    0.41
    ToLoad
    0.40
    pretation
    0.40
    tze
    0.40
    asantry
    0.40
    Activations Density 0.474%

    No Known Activations